Populating an Allergens Ontology Using Natural Language Processing and Machine Learning Techniques

Valarakos, Alexandros G.; Karkaletsis, Vangelis; Alexopoulou, Dimitra; Papadimitriou, Elsa; Spyropoulos, Constantine D.

doi:10.1007/11527770_38

Cited by 2 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A more robust knowledge extraction pipeline is being developed that will mine abstracts listed in PubMed for relevance to any age, and find any of the predefined relationships to phenotype, such as different diseases. For this next stage, existing information extraction techniques and programs [ 15 , 16 ] will be used with their possible adaptation to this specific use.…”

Section: Discussionmentioning

confidence: 99%

Towards an Age-Phenome Knowledge-base

Geifman¹,

Rubin²

2011

BMC Bioinformatics

View full text Add to dashboard Cite

BackgroundCurrently, data about age-phenotype associations are not systematically organized and cannot be studied methodically. Searching for scientific articles describing phenotypic changes reported as occurring at a given age is not possible for most ages.ResultsHere we present the Age-Phenome Knowledge-base (APK), in which knowledge about age-related phenotypic patterns and events can be modeled and stored for retrieval. The APK contains evidence connecting specific ages or age groups with phenotypes, such as disease and clinical traits. Using a simple text mining tool developed for this purpose, we extracted instances of age-phenotype associations from journal abstracts related to non-insulin-dependent Diabetes Mellitus. In addition, links between age and phenotype were extracted from clinical data obtained from the NHANES III survey. The knowledge stored in the APK is made available for the relevant research community in the form of 'Age-Cards', each card holds the collection of all the information stored in the APK about a particular age. These Age-Cards are presented in a wiki, allowing community review, amendment and contribution of additional information. In addition to the wiki interaction, complex searches can also be conducted which require the user to have some knowledge of database query construction.ConclusionsThe combination of a knowledge model based repository with community participation in the evolution and refinement of the knowledge-base makes the APK a useful and valuable environment for collecting and curating existing knowledge of the connections between age and phenotypes.

show abstract

Section: Discussionmentioning

confidence: 99%